FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2238729327> ?p ?o ?g. }

• W2238729327 abstract "This thesis presents a machine learning approach to Word Sense Disambiguation (WSD), the task that consists in selecting the correct sense of an ambiguous word in a given context.We recast the task of disambiguating polysemous nouns as a multilingual classification task. Instead of using a predefined monolingual sense inventory such as WordNet, we use a language-independent framework where the word senses are derived automatically from word alignments on a parallel corpus. As a consequence, the task is turned into a cross-lingual WSD task, that consists in selecting the contextually correct translation of an ambiguous target word.In order to evaluate the viability of cross-lingual Word Sense Disambiguation, we constructed a lexical sample data set of twenty ambiguous nouns. For the creation of the multilingual sense inventory, we first applied word alignment to a six-lingual parallel corpus and manually clustered the obtained translations by meaning for all target words. The resulting multilingual sense inventory then served as the basis for the annotation of the test data. The ParaSense WSD system we propose in this thesis presents a truly multilingual classification-based approach to WSD that directly incorporates evidence from four other languages. We built five classifiers with English as an input language and translations in the five supported languages (viz. French, Dutch, Italian, Spanish and German) as classification output. The feature vectors incorporate both local context features as well as translation features that are extracted from the aligned translations.The hypothesis underlying the construction of a multilingual WSD system is that adding translational evidence from multiple languages will be more informative than using only monolingual or bilingual information. We believe it is possible to use the differences between the languages to obtain certain leverage on word meanings and better disambiguate a polysemous word in a given context.The experimental results confirm the validity of our approach: the classifiers that employ translational evidence constantly outperform the classifiers that only exploit local context information for four out of five target languages, viz. French, Spanish, German and Dutch. Furthermore, a comparison with all systems that participated in a dedicated cross-lingual Word Sense Disambiguation competition revealed that the ParaSense system outperforms all other systems for all five target languages.As our system extracts all information from the parallel corpus at hand, it is a very flexible and language-independent approach that allows to bypass the knowledge acquisition bottleneck for Word Sense Disambiguation." @default.
• W2238729327 created "2016-06-24" @default.
• W2238729327 creator A5023493215 @default.
• W2238729327 date "2012-01-01" @default.
• W2238729327 modified "2023-09-23" @default.
• W2238729327 title "ParaSense: parallel corpora for word sense disambiguation" @default.
• W2238729327 cites W1590350164 @default.
• W2238729327 cites W1731542712 @default.
• W2238729327 cites W1792843900 @default.
• W2238729327 cites W2004225329 @default.
• W2238729327 cites W2077654158 @default.
• W2238729327 cites W2095980407 @default.
• W2238729327 cites W2100044354 @default.
• W2238729327 cites W2101105183 @default.
• W2238729327 cites W2128809169 @default.
• W2238729327 cites W2136565384 @default.
• W2238729327 cites W2231213561 @default.
• W2238729327 cites W2251927781 @default.
• W2238729327 cites W2304016852 @default.
• W2238729327 cites W2305265098 @default.
• W2238729327 cites W2611353417 @default.
• W2238729327 cites W2893578842 @default.
• W2238729327 cites W170578315 @default.
• W2238729327 hasPublicationYear "2012" @default.
• W2238729327 type Work @default.
• W2238729327 sameAs 2238729327 @default.
• W2238729327 citedByCount "3" @default.
• W2238729327 countsByYear W22387293272013 @default.
• W2238729327 countsByYear W22387293272019 @default.
• W2238729327 crossrefType "dissertation" @default.
• W2238729327 hasAuthorship W2238729327A5023493215 @default.
• W2238729327 hasConcept C121934690 @default.
• W2238729327 hasConcept C138885662 @default.
• W2238729327 hasConcept C151730666 @default.
• W2238729327 hasConcept C154945302 @default.
• W2238729327 hasConcept C157659113 @default.
• W2238729327 hasConcept C162324750 @default.
• W2238729327 hasConcept C177264268 @default.
• W2238729327 hasConcept C187736073 @default.
• W2238729327 hasConcept C199360897 @default.
• W2238729327 hasConcept C203005215 @default.
• W2238729327 hasConcept C204321447 @default.
• W2238729327 hasConcept C2779343474 @default.
• W2238729327 hasConcept C2780451532 @default.
• W2238729327 hasConcept C41008148 @default.
• W2238729327 hasConcept C41895202 @default.
• W2238729327 hasConcept C44572571 @default.
• W2238729327 hasConcept C86803240 @default.
• W2238729327 hasConcept C90805587 @default.
• W2238729327 hasConceptScore W2238729327C121934690 @default.
• W2238729327 hasConceptScore W2238729327C138885662 @default.
• W2238729327 hasConceptScore W2238729327C151730666 @default.
• W2238729327 hasConceptScore W2238729327C154945302 @default.
• W2238729327 hasConceptScore W2238729327C157659113 @default.
• W2238729327 hasConceptScore W2238729327C162324750 @default.
• W2238729327 hasConceptScore W2238729327C177264268 @default.
• W2238729327 hasConceptScore W2238729327C187736073 @default.
• W2238729327 hasConceptScore W2238729327C199360897 @default.
• W2238729327 hasConceptScore W2238729327C203005215 @default.
• W2238729327 hasConceptScore W2238729327C204321447 @default.
• W2238729327 hasConceptScore W2238729327C2779343474 @default.
• W2238729327 hasConceptScore W2238729327C2780451532 @default.
• W2238729327 hasConceptScore W2238729327C41008148 @default.
• W2238729327 hasConceptScore W2238729327C41895202 @default.
• W2238729327 hasConceptScore W2238729327C44572571 @default.
• W2238729327 hasConceptScore W2238729327C86803240 @default.
• W2238729327 hasConceptScore W2238729327C90805587 @default.
• W2238729327 hasLocation W22387293271 @default.
• W2238729327 hasOpenAccess W2238729327 @default.
• W2238729327 hasPrimaryLocation W22387293271 @default.
• W2238729327 hasRelatedWork W1481149166 @default.
• W2238729327 hasRelatedWork W1543182268 @default.
• W2238729327 hasRelatedWork W1574012512 @default.
• W2238729327 hasRelatedWork W1662612805 @default.
• W2238729327 hasRelatedWork W175991105 @default.
• W2238729327 hasRelatedWork W1792843900 @default.
• W2238729327 hasRelatedWork W1914279426 @default.
• W2238729327 hasRelatedWork W1987562605 @default.
• W2238729327 hasRelatedWork W1989563023 @default.
• W2238729327 hasRelatedWork W2035959783 @default.
• W2238729327 hasRelatedWork W2040930890 @default.
• W2238729327 hasRelatedWork W2081523373 @default.
• W2238729327 hasRelatedWork W2101454539 @default.
• W2238729327 hasRelatedWork W2125082006 @default.
• W2238729327 hasRelatedWork W2152952720 @default.
• W2238729327 hasRelatedWork W2245545634 @default.
• W2238729327 hasRelatedWork W2292964953 @default.
• W2238729327 hasRelatedWork W2945447230 @default.
• W2238729327 hasRelatedWork W334895485 @default.
• W2238729327 hasRelatedWork W2183678764 @default.
• W2238729327 isParatext "false" @default.
• W2238729327 isRetracted "false" @default.
• W2238729327 magId "2238729327" @default.
• W2238729327 workType "dissertation" @default.